The skeletal position of a pitcher at the moment of foot strike in the delivery of a pitch is compared against a plurality of skeletal positions, the plurality of skeletal positions being associated with a plurality of pitchers, each skeletal position being associated with the moment of foot strike in the delivery of a pitch. A value representative of a position of the pitch on a spectrum is provided, the spectrum being defined by a characteristic known about each of the pitchers of the plurality, the characteristic being Tommy John surgery or maximum fastball speed.

An Internet of Thing (IoT) sport device includes a body with a processor, a camera and a wireless transceiver coupled to the processor.

During a first time period and for a first user, a second user is automatically selected based on competitive data of the first user and competitive data of the second user, and a workout selection is sent to cause a video of a workout to be displayed during a second time period on a smart mirror of the first user and a smart mirror of the second user. During the second time period, a live stream of the first user exercising is displayed at the smart mirror of the second user, and a live stream of the second user exercising is received and displayed at the smart mirror of the first user. During the second time period, a performance score of the first user and a performance score of the second user is displayed at the smart mirrors of the first user and the second user.

A user-specific workout can be generated by adjusting transform parameters of a user-agnostic training profile to conform to a user boundary specifying a user's ability to perform work. The user-agnostic training profile can be defined in a training space, specifying a power curve in a time domain whereas the user boundary can be defined in a boundary space, specifying amounts of user-produced work in a time window size domain. A training boundary can be generated based on the user-agnostic training profile by determining the largest area under the user-agnostic training profile power curve for various time window sizes, where each largest area under the user-agnostic training profile power curve produces a data point for the training boundary for that window size domain value. The training boundary can be transformed based on the user boundary, causing corresponding transformations to the user-agnostics training profile, converting it to a user-specific workout.

Evaluation value calculation unit calculates, based on time-series changes in exercise information on each of a plurality of users who have exercised in accordance with an exercise menu, an evaluation value of the exercise menu. Evaluation result generation unit compares an evaluation value of an exercise menu with a reference value. The evaluation result generation unit generates results of evaluating the exercise menu based on the results of comparing the evaluation value with the reference value.

A method is disclosed for using an artificial intelligence engine to modify resistance of pedals of an exercise device. The method includes generating, by the artificial intelligence engine, a machine learning model trained to receive measurements as input, and outputting, based on the measurements, a control instruction that causes the exercise device to modify, independently from each other, the resistance of the pedals. While a user performs an exercise using the exercise device, the method includes receiving the measurements from sensors associated with the pedals. The method includes determining, based on the measurements, a quantifiable or qualitative modification to the resistance provided by a pedal of the pedals. The resistance provided by another pedal of the pedals is not modified. The method includes transmitting the control instruction to the exercise device to cause the resistance provided by the pedal to be modified.

Ergonomics improvement systems having wearable sensors and related methods. An example ergonomics improvement system includes an encoder system to couple to a limb of a body. The encoder sensor system to generate first outputs in response to movement of the limb relative to the body to determine a position of the limb relative to the body. The system includes a load sensor to generate a second output representative of a load carried by the body and a position sensor to generate a third output representative of a position of a right foot of the body relative to a position of a left foot of the body.

A timely component movement measuring system for a vehicle is disclosed. The system includes a component of a vehicle, the component having a range of motion. The system also includes a sensor to measure a movement of the component through some or all of the range of motion of the component.

In a first aspect, a method for monitoring a golf swing is provided that includes coupling a mobile telephone to a golf club and employing the mobile telephone coupled to the golf club to monitor acceleration of the mobile telephone as the mobile telephone swings while a user swings the golf club, collect acceleration information based on the monitored acceleration of the mobile telephone as the mobile telephone swings, analyze the collected acceleration information to determine one or more characteristics of the golf swing based on the collected acceleration information, and output information regarding the one or more characteristics of the golf swing on the display of the mobile telephone. Numerous other aspects are provided.

A pedal drive system, in particular for an electric vehicle or a training apparatus, and for generating electrical power from muscle power of a user with at least one pedal and an electric generator, connected mechanically with said at least one pedal, is provided. To improve the haptic feel and feedback at the pedal, a control unit is provided for controlling a feedback torque, applied at said pedal, wherein the control unit comprises a haptic renderer, configured for control of said feedback torque based on at least one user-defined pedal reference trajectory.